A Solar-Powered Battery Charging System Using Levenberg-Marquard Algorithum

Abstract Neural control is a branch of the general field of intelligent control which is based on the concept of artificial intelligence. Neural controller can operate at different conditions of load current at different orbital periods without any tuning such in case of PID controller. So an artificial neural network ANN based model has been developed for the optimum operation of power system. In this a boost converter is used. The controlled boost converter is used as an interface between photovoltaic PV panels and the loads connected to them. It converts any input voltage within its operating range into a constant output voltage that is suitable for load feeding. An ANN is trained using a back propagation with Levenberg-Marquardt algorithm. Neural network controller architecture gives satisfactory result with small number of neuron hence battery in terms of memory and time are required for neural network controller implementation. To implement the neural network into hardware design it is required to translate generated mode into device structure. VHDL language is used to describe those networks into hardware. Hardware Descriptive Language code has been proposed to implement ANNs as well as to present simulation results. Field programmable gate array FPGA is a digital device which helped in reprogrammable properties and robust flexibility. With low precision artificial neural network design FPGAs have higher speed and smaller size for real time application than the VLSI and DSP chips